Papers Visual Entailment
“Visual Entailment” 태그가 달린 논문 61편 · 필터 해제
CogRad: A Cognitively-Inspired Multi-Agent Framework for Radiology Report Generation
Automated radiology report generation (RRG) can ease radiologist workload, yet most existing systems produce a report in a single forward pass, with no mechanism to check a claim against the image or revisit a finding on…
Visual EntailmentVisual GroundingAn Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no gr…
Visual EntailmentCode GenerationDataset Creation for Visual Entailment using Generative AI
In this paper we present and validate a new synthetic dataset for training visual entailment models. Existing datasets for visual entailment are small and sparse compared to datasets for textual entailment. Manually crea…
Visual EntailmentProbing Vision-Language Understanding through the Visual Entailment Task: promises and pitfalls
This study investigates the extent to which the Visual Entailment (VE) task serves as a reliable probe of vision-language understanding in multimodal language models, using the LLaMA 3.2 11B Vision model as a test case. …
Visual EntailmentVisual GroundingCOREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark
Recently, many benchmarks and datasets have been developed to evaluate Vision-Language Models (VLMs) using visual question answering (VQA) pairs, and models have shown significant accuracy improvements. However, these be…
Visual Question AnsweringVisual EntailmentDefeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization
We introduce a new task called Defeasible Visual Entailment (DVE), where the goal is to allow the modification of the entailment relationship between an image premise and a text hypothesis based on an additional update. …
Contrastive LearningDecision MakingNatural Language InferenceQuestion Answering+2VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research on the domain generalizability of deep l…
Deep LearningDomain GeneralizationImage CaptioningLanguage Modeling+6Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation
Grounded Multimodal Named Entity Recognition (GMNER) task aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging attributes: 1) The tenuous correlation b…
Grounded Multimodal Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognitionobject-detection+5Understanding Figurative Meaning through Explainable Visual Entailment
Large Vision-Language Models (VLMs) have demonstrated strong capabilities in tasks requiring a fine-grained understanding of literal meaning in images and text, such as visual question-answering or visual entailment. How…
Question AnsweringVisual EntailmentVisual Question AnsweringMoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
Despite the demonstrated parameter efficiency of prompt-based multimodal fusion methods, their limited adaptivity and expressiveness often result in suboptimal performance compared to other tuning approaches. In this pap…
DisentanglementMultimodal Deep LearningVisual EntailmentVEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence. The goal is to predict whether the image sem…
Multimodal ReasoningSentenceVisual EntailmentArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks
"A data scientist is tasked with developing a low-cost surgical VQA system for a 2-month workshop. Due to data sensitivity, she collects 50 hours of surgical video from a hospital, requiring two months for privacy approv…
Domain GeneralizationImage CaptioningQuestion AnsweringVisual Entailment+2LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition
Grounded Multimodal Named Entity Recognition (GMNER) is a nascent multimodal task that aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging properties:…
Grounded Multimodal Named Entity RecognitionMulti-modal Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition+6p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks. In light of the rapidly increasing size of pre-trained VLMs, parameter-efficient transfer l…
Image CaptioningQuestion AnsweringTransfer LearningVisual Entailment+1Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
Recent advancements in large vision-language models (LVLMs) have led to significant progress in generating natural language descriptions for visual content and thus enhancing various applications. One issue with these po…
Factual Inconsistency Detection in Chart CaptioningImage CaptioningVisual EntailmentGood Questions Help Zero-Shot Image Reasoning
Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained…
Fine-Grained Image ClassificationQuestion AnsweringVisual EntailmentVisual Question AnsweringLightweight In-Context Tuning for Multimodal Unified Models
In-context learning (ICL) involves reasoning from given contextual examples. As more modalities comes, this procedure is becoming more challenging as the interleaved input modalities convolutes the understanding process.…
Image CaptioningIn-Context LearningQuestion AnsweringVisual Entailment+2Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages
Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and…
Image-text RetrievalMachine TranslationRetrievalText Retrieval+2"Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning
Well-formed context aware image captions and tags in enterprise content such as marketing material are critical to ensure their brand presence and content recall. Manual creation and updates to ensure the same is non tri…
Image CaptioningKeyword ExtractionMarketingVisual EntailmentI Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the s…
Visual Entailment